DCoM: A Deep Column Mapper for Semantic Data Type Detection
This addresses the need for robust and scalable data type detection in data cleaning and management, though it is incremental as it builds on deep learning approaches.
The paper tackles the problem of semantic data type detection for data science tasks by introducing DCoM, a multi-input NLP-based deep neural network that processes raw column values as text, which outperforms existing methods on a dataset of 686,765 columns with 78 types.
Detection of semantic data types is a very crucial task in data science for automated data cleaning, schema matching, data discovery, semantic data type normalization and sensitive data identification. Existing methods include regular expression-based or dictionary lookup-based methods that are not robust to dirty as well unseen data and are limited to a very less number of semantic data types to predict. Existing Machine Learning methods extract large number of engineered features from data and build logistic regression, random forest or feedforward neural network for this purpose. In this paper, we introduce DCoM, a collection of multi-input NLP-based deep neural networks to detect semantic data types where instead of extracting large number of features from the data, we feed the raw values of columns (or instances) to the model as texts. We train DCoM on 686,765 data columns extracted from VizNet corpus with 78 different semantic data types. DCoM outperforms other contemporary results with a quite significant margin on the same dataset.